Memory#
Action Space |
|
Observation Space |
|
Reward Range |
|
Creation |
|
Description#
This environment is a memory test. The agent starts in a small room where it sees an object. It then has to go through a narrow hallway which ends in a split. At each end of the split there is an object, one of which is the same as the object in the starting room. The agent has to remember the initial object, and go to the matching object at split.
Mission Space#
“go to the matching object at the end of the hallway”
Action Space#
Num |
Name |
Action |
---|---|---|
0 |
left |
Turn left |
1 |
right |
Turn right |
2 |
forward |
Move forward |
3 |
pickup |
Pick up an object |
4 |
drop |
Unused |
5 |
toggle |
Toggle/activate an object |
6 |
done |
Unused |
Observation Encoding#
Each tile is encoded as a 3 dimensional tuple:
(OBJECT_IDX, COLOR_IDX, STATE)
OBJECT_TO_IDX
andCOLOR_TO_IDX
mapping can be found in minigrid/core/constants.pySTATE
refers to the door state with 0=open, 1=closed and 2=locked
Rewards#
A reward of ‘1 - 0.9 * (step_count / max_steps)’ is given for success, and ‘0’ for failure.
Termination#
The episode ends if any one of the following conditions is met:
The agent reaches the correct matching object.
The agent reaches the wrong matching object.
Timeout (see
max_steps
).
Registered Configurations#
S: size of map SxS.
MiniGrid-MemoryS17Random-v0
MiniGrid-MemoryS13Random-v0
MiniGrid-MemoryS13-v0
MiniGrid-MemoryS11-v0